Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 24577
    Prev
    Next
    INDEX
    Explanations

    programming language elements related to the structure and flow of code execution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
      
    -0.49
     weak
    -0.42
    ium
    -0.42
    +#+#
    -0.42
    azzo
    -0.40
     face
    -0.40
    Reprodução
    -0.40
    inum
    -0.40
     F
    -0.39
    umann
    -0.38
    POSITIVE LOGITS
     ſta
    0.67
     noDo
    0.63
    MessageTagHelper
    0.58
    HasAnnotation
    0.58
     houſe
    0.57
    ="@+
    0.56
     الرياضيه
    0.56
     pleaſure
    0.56
     Италијани
    0.55
    expandindo
    0.55
    Activations Density 0.050%

    No Known Activations